ModelBridge

ModelBridge

中文文档 | 配置参考

ModelBridge is a Gin-based LLM API protocol bridge. It accepts requests in the OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini, or Ollama Chat schemas, converts them through a shared internal representation, and forwards them to one configured upstream.

Quick Start

Install:

curl -fsSL https://cnb.cool/Bring/Project/Series/ModelBridge/-/git/raw/main/install.sh | sh

Windows PowerShell:

irm https://cnb.cool/Bring/Project/Series/ModelBridge/-/git/raw/main/install.ps1 | iex

Run against an OpenAI-compatible upstream:

TARGET_PROTOCOL=openai-chat \
TARGET_BASE_URL=https://api.openai.com/v1 \
TARGET_TOKEN="$OPENAI_API_KEY" \
go run ./cmd/server

TARGET_TOKEN may be empty for local or unauthenticated upstreams, or when client authentication should pass through to the upstream. See CONFIG.md for the full environment-variable reference.

Health check:

curl http://localhost:8080/healthz

Supported Protocols

Inbound routes:

Target protocols:

• openai-chat
• openai-responses
• claude
• gemini
• ollama

Examples

OpenAI Chat inbound:

curl http://localhost:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-4.1-mini",
    "messages": [{"role": "user", "content": "hello"}]
  }'

Streaming:

curl -N http://localhost:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-4.1-mini",
    "stream": true,
    "messages": [{"role": "user", "content": "stream a short answer"}]
  }'

Model list:

curl http://localhost:8080/v1/models

ModelBridge fetches models from the configured target and writes the response in the inbound client protocol's schema. More model-list options are documented in CONFIG.md.

Docker

docker run --rm -p 8080:8080 \
  -e TARGET_PROTOCOL=openai-chat \
  -e TARGET_BASE_URL=https://api.openai.com/v1 \
  -e TARGET_TOKEN="$OPENAI_API_KEY" \
  docker.cnb.cool/bring/project/series/modelbridge:latest

Development

go test ./...
go test -coverprofile=coverage.out -covermode=atomic ./...

Smoke and benchmark workflows are documented in docs/verification.md.

License

Licensed under the Apache License 2.0.

Copyright 2026 leun